-
Notifications
You must be signed in to change notification settings - Fork 1.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add Calibtool for GluonCV #893
Conversation
ssd_512_vgg16_atrous_voc | 215.05 | 32.63 | 6.76 | 36.56 | 78.82 | 78.82 | ||
ssd_512_mobilenet1.0_voc | 28.98 | 6.97 | 65.55 | 210.17 | 75.51 | 75.49 | ||
ssd_512_resnet50_v1_voc | 52.77 | 11.75 | 28.68 | 143.61 | 80.24 | 80.23 | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Add FCN?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Okay, I'll apply calibtool to fcn.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Now, there is very little content displayed in README
of segmentation part. I can work on FCN part with @xinyu-intel.
Job PR-893-3 is done. |
Job PR-893-4 is done. |
Job PR-893-5 is done. |
Job PR-893-6 is done. |
Job PR-893-7 is done. |
requesting @hetong007 for review as imagenet part is involved |
Thanks for approval. Merging now:) |
Pending on apache/mxnet#15754
Add
quantize_net()
function for quantizing a gluon hybridblock and enabled in imagenet_classification and ssd models. More models are under evaluation.UT is ready.
Docs are WIP.
@pengzhao-intel @zhreshold @wuxun-zhang